Artificial Intelligence Engineer

Simform; Ahmedabad District; On-site; INR 2,800,000 - 4,500,000; Full time

Job summary

Simform is seeking a Senior AI Engineer in India to design, develop, and deploy production-grade Generative AI solutions. You will work on LLM-driven apps, RAG pipelines, and AI agents within enterprise-scale architectures.

You will leverage LangChain/LangGraph, embeddings, and cloud deployments (Azure/AWS/GCP) while ensuring reliability, scalability, and code quality. Mentorship of juniors and cross-functional collaboration are key aspects of the role.

Qualifications

• 4–7 years in AI/ML development and software engineering.
• Strong Python and ML framework skills (PyTorch, TensorFlow, scikit-learn).
• Hands-on with LLMs, Generative AI, RAG, embeddings, and vector databases.
• Experience with LangChain, LangGraph, or equivalent LLM orchestration frameworks.
• Knowledge of APIs, automated testing, Git, CI/CD, cloud deployments.

Responsibilities

• Design and develop Generative AI applications using LLMs, prompt engineering, and structured outputs.
• Build advanced RAG pipelines using embeddings, hybrid search, reranking, and vector databases.
• Develop AI agents and workflows using LangGraph, LangChain, tool calling, and MCP where appropriate.
• Develop and deploy enterprise level applications using Azure AI services.
• Implement AI evaluation frameworks, automated regression testing, and quality metrics.

Skills

Python

ML fundamentals

Model evaluation

NLP

Education

Bachelor's/Master's in CS/AI

Tools

PyTorch

TensorFlow

scikit-learn

LangChain

LangGraph

Docker

Kubernetes

Job description

We are looking for a Senior AI Engineer with expertise in Generative AI, Agentic AI, LLMs, and RAG architectures, complemented by a solid foundation in traditional machine learning. You will build, evaluate, and deploy production-grade AI solutions with a strong focus on reliability, scalability, and code quality.

Key Responsibilities

• Design and develop Generative AI applications using LLMs, prompt engineering, and structured outputs.
• Build advanced RAG pipelines using embeddings, hybrid search, reranking, and vector databases.
• Develop AI agents and workflows using LangGraph, LangChain, tool calling, and MCP where appropriate.
• Develop and deploy enterprise level applications using Azure AI services.
• Implement AI evaluation frameworks, automated regression testing, and quality metrics to assess accuracy, relevance, faithfulness, and task completion.
• Apply traditional ML techniques for classification, regression, predictive analytics, and NLP where required.
• Build data preprocessing, feature engineering, model training, and evaluation pipelines.
• Write clean, modular, testable, and maintainable Python code following software engineering best practices.
• Integrate AI solutions into production systems through APIs, with appropriate security, monitoring, and observability.
• Deploy and optimize AI applications on AWS, Azure, or GCP.
• Collaborate with cross-functional teams, contribute to architecture decisions, and mentor junior engineers.

Required Skills & Qualifications

• Bachelor's or Master's degree in Computer Science, AI/ML, or a related field.
• 4–7 years of experience in AI/ML development and software engineering.
• Strong Python programming skills and experience with PyTorch, TensorFlow, or scikit-learn.
• Understanding of machine learning fundamentals, including classification, regression, model evaluation, and feature engineering.
• Hands‑on experience with LLMs, Generative AI, RAG, embeddings, and vector databases.
• Experience with LangChain, LangGraph, or equivalent LLM orchestration frameworks.
• Understanding of AI agents, tool calling, workflow orchestration, and failure handling.
• Familiarity with evaluation frameworks such as RAGAS, DeepEval, or equivalent tools.
• Experience with APIs, automated testing, Git, CI/CD, databases, and cloud deployments.
• Knowledge of production monitoring, debugging, security, and performance optimization.

Preferred Qualifications

• Experience with MCP, GraphRAG, multi-agent systems, and advanced retrieval techniques.
• Knowledge of LLM fine‑tuning, LoRA/PEFT, and model optimization.
• Familiarity with Langfuse, LangSmith, Arize Phoenix, MLflow, Docker, and Kubernetes.
• Exposure to computer vision, multimodal AI, and MLOps/LLMOps practices.